Abstract
Reliability is an important characteristic of any system. Healthcare systems are typical examples of such systems. In reliability engineering, such systems are considered as complex, inhomogeneous, and uncertain, and require special mathematical representations. The structure function is a suitable model representing real systems. Methods of system reliability evaluation based on the structure function are well established but deterministic. This restricts its use for uncertain or incomplete data. A structure function can be created only for system in which correlations of all components are indicated and all component states are known. In this paper, a new method for structure function construction is proposed. Incomplete data is analysed using Fuzzy Decision Trees (FDTs), where input and output attributes are interpreted as component states and values of the structure function, respectively. This method is applied to reliability analysis of healthcare system. For illustration, we considered the system laparoscopic surgery that has 4 components and 36 state vectors. In addition we evaluate proposed method by 3 benchmark's systems with 243, 108, and 512 state vectors, respectively. Two of these benchmarks have 5 components and one has 4 components. Uncertainty is simulated by randomly deleting between 5% and 90% of all state vectors before constructing the structure function. With 50% of deleted stages, the error rate is below 0.2% for all three systems. We conclude that FDT-based reliability analysis is applicable for incomplete data in medical systems, too.
Highlights
THE investigation in reliability engineering of healthcare system has started as analysis of medical devices and equipment [1]
We take into account the uncertainties of initial data and suggest a method that is based on the Fuzzy Decision Tree (FDT)
The main contribution of this paper is that we have developed novel and original method for the construction of the structure function based on incompletely specified and ambiguous data
Summary
THE investigation in reliability engineering of healthcare system has started as analysis of medical devices and equipment [1]. A healthcare system includes components of different types, such as technical components (equipment/devises) and the human factor This system is inhomogenous in the view of reliability engineering [3, 4, 7], and the construction of mathematical representation including all types of component become challenging [3, 7, 10]. We take into account the uncertainties of initial data and suggest a method that is based on the Fuzzy Decision Tree (FDT). FDTs allow to take into account uncertainties caused by incompletely specified data This is still possible if it is expensive to obtain all data about the real system’s behavior, if there is only sparse data, or if data s acquired incompletely due to poor documentation. The use of FDTs for the construction of the structure function assumes the induction of a tree that is based on the data (fuzzy and/or crisp).
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
